WhatsApp AI Assistant Powered by RAG — Turn Your Google Drive Into a Smart Knowledge Base

We're an internal members' organization looking to build a WhatsApp-based AI assistant that lets our team get instant, accurate answers pulled directly from our existing Google Drive documents — no more digging through folders or asking around. What the Assistant Needs to Do Connect to WhatsApp Business as the main interface Use OpenAI to generate answers grounded in our knowledge base (RAG-based, not freeform) Read and understand content from PDFs, Google Docs, and Google Sheets Always cite the source document when answering, so users can verify or dig deeper Let non-technical admins update the knowledge base just by adding/editing files in Drive — no code, no manual re-indexing steps beyond a simple sync trigger Include a straightforward "refresh knowledge base" mechanism after documents are updated Recognize when it's not confident in an answer and escalate to a human instead of guessing Ideal Technical Background Strong hands-on experience with the OpenAI API WhatsApp Business API integration experience Solid understanding of RAG architectures and vector databases (Pinecone, Weaviate, Qdrant, etc.) Comfortable in Python or Node.js Experience with LangChain, LangGraph, or similar orchestration frameworks n8n or Make.com experience is a strong plus for the sync/automation layer Why This Project This isn't a one-off chatbot — it's meant to become the go-to internal tool our members rely on daily. We're looking for someone who can architect this properly from day one so it stays maintainable and easy to extend later. To Apply Please share relevant past projects, especially anything involving RAG pipelines, WhatsApp integrations, or Google Drive-based knowledge systems.